"Exploring Biometrics Through the Lens of Generative AI and Large Vision-Language Models"

Presentation by Dr. Vishal Patel, Johns Hopkins University

Talk Abstract:

Recent advances in Generative AI and Large Vision-Language Models (LVLMs) are transforming the field of biometrics, enabling new possibilities in face analysis, identity verification, and synthetic data generation. In this talk, I will explore the intersection of generative AI and biometrics, highlighting how these models enhance facial recognition, attribute prediction, and other critical tasks. While these advancements bring unprecedented capabilities, they also raise concerns about data replication, privacy, and bias. I will discuss key challenges in mitigating these issues and present our recent work on LLM-based facial analysis, demonstrating how foundation models can be leveraged for robust and interpretable biometric applications. This talk will provide insights into both the opportunities and ethical considerations of generative AI in biometrics, paving the way for future research in responsible and secure biometric AI.

Bio:

Vishal M. Patel is an Associate Professor in the Department of Electrical and Computer Engineering (ECE) at Johns Hopkins University. His research focuses on computer vision, machine learning, image processing, medical image analysis, and biometrics. He has received a number of awards including the 2021 IEEE Signal Processing Society (SPS) Pierre-Simon Laplace Early Career Technical Achievement Award, the 2021 NSF CAREER Award, the 2021 IAPR Young Biometrics Investigator Award (YBIA), the 2016 ONR Young Investigator Award, and the 2016 Jimmy Lin Award for Invention. Patel serves as an associate editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence journal and IEEE Transactions on Biometrics, Behavior, and Identity Science.  He also chairs the conference subcommittee of IAPR Technical Committee on Biometrics (TC4).  He is a fellow of the IAPR.